Instructions to use Naphula/Quantum-Precog-24B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Naphula/Quantum-Precog-24B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Naphula/Quantum-Precog-24B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Naphula/Quantum-Precog-24B")
model = AutoModelForCausalLM.from_pretrained("Naphula/Quantum-Precog-24B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Naphula/Quantum-Precog-24B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Naphula/Quantum-Precog-24B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Naphula/Quantum-Precog-24B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Naphula/Quantum-Precog-24B

SGLang

How to use Naphula/Quantum-Precog-24B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Naphula/Quantum-Precog-24B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Naphula/Quantum-Precog-24B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Naphula/Quantum-Precog-24B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Naphula/Quantum-Precog-24B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Naphula/Quantum-Precog-24B with Docker Model Runner:
```
docker model run hf.co/Naphula/Quantum-Precog-24B
```

Sneaky

by redaihf - opened 2 days ago

Discussion

redaihf

2 days ago

•

edited 2 days ago

This model is not fully compliant although it does appear to have no refusals. It tends to grumble in a manner which ignores the context ("criminal", "hell", "barbaric") or to provide artificially shortened responses similar to Jbliterated Llama albeit with more subtlety. However when it does respond properly it writes in a refreshing manner with a distinct lack of slop.

redaihf

2 days ago

It is probably worth re-running this merge recipe with some abliterated donors:

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment